Neural Networks
Neural computing has emerged, in the last two decades, as a practical technology with many successful applications in many fields, the majority of which come from the field of pattern recognition. Neural network models are derived by emulating the functionality of the human brain. Evolutionary computation techniques are approaches inspired by biological evolution mechanisms such as reproduction, crossover, and mutation and they have been applied in a variety of optimization problems. The marriage of neural networks and evolutionary techniques results in approaches referred to as neuro-evolutionary techniques.
Keywords that describe the current research in the lab within the context of Neural Networks are: Neural Network Classification Models, Adaptive Resonance Theory, Neuro-Evolution, Multi-Objective Optimization.
In this work, we present the evolution of ART Neural Network architectures (classifiers) using a multiobjective optimization approach. In particular, we propose the use of a multiobjective evolutionary approach to simultaneously evolve the weights and the topology of three well-known ART architectures; Fuzzy ARTMAP (FAM), Ellipsoidal ARTMAP (EAM) and Gaussian ARTMAP (GAM). We refer to the resulting architectures as MO-GFAM, MOGEAM, and MO-GGAM, and collectively as MO-GART. The major advantage of MO-GART is that it produces a number of solutions for the classification problem at hand that have different levels of merit (accuracy on unseen data (generalization) and size (number of categories created)). MO-GART is shown to be more elegant (does not require user intervention to define the network parameters), more effective (of better accuracy and smaller size), and more efficient (faster to produce the solution networks) than other ART neural network architectures that have appeared in the literature. Furthermore, MO-GART is shown to be competitive with other popular classifiers, such as CART and SVMs.
- Michael Georgiopoulos
- Georgios Anagnostopoulos
- Cong Li
- Talitha Rubio
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks is one of the premier journals in the neural network field, published by IEEE.
IEEE Transactions on Neural Networks was the 7th most cited journal in electrical and electronics engineering in 2007, according to the annual Journal Citation Report (2007 edition), published by the Institute for Scientific Information. Read more at http://www.ieee.org/products/citations.html.
Devoted to the science and technology of neural networks, which disclose significant technical knowledge, exploratory developments, and applications of neural networks from biology to software to hardware. Emphasis is on artificial neural networks.
Neural Networks Journal
Neural Networks is another premier journal in the neural network area, published by Elsevier.
The Journal Citation Reports¨ 2009, published by Thomson Reuters, in the Category of Computer Science, Artificial Intelligence, have just been released. The Neural Networks journal Impact Factor in 2008 is 2.656. In 2007 its impact facto was 1.951. The impact factor in 2007 is calculated by dividing the number of citations of papers that appeared in the Neural Networks journal in 2006 and 2007 with the actual number of papers that appeared in the Neural Networks journal over the same time period.
Neural Computation Journal
Neural Computation is the 3rd premier journal in the neural network area, published by MIT Press.
Neural Computation disseminates important, multidisciplinary research in a field that attracts psychologists, physicists, computer scientists, neuroscientists, and artificial intelligence investigators, among others. For researchers looking at the scientific and engineering challenges of understanding the brain and building computers, Neural Computation highlights common problems and techniques in modeling the brain, and in the design and construction of neurally-inspired information processing systems.
Evolutionary Computation Journal
Evolutionary Computation journal is a journal published by MIT Press.
Evolutionary Computationprovides an international forum for facilitating and enhancing the exchange of information among researchers involved in both the theoretical and practical aspects of computational systems of an evolutionary nature.
IEEE Transactions on Evolutionary Computation
The Transactions on Evolutionary Computation is published by IEEE.
This journal is devoted to the theory, design and applications of evolutionary computation, with emphasis given to engineering systems and scientific applications encompassing, but not limited to, evolutionary optimization, machine learning, intelligent systems design, image processing and machine vision, pattern recognition, evolutionary neurocomputing, evolutionary fuzzy systems, applications in biomedicine and biochemistry, robotics and control, mathematical modeling, civil, chemical, aeronautical, and industrial engineering applications.
International Joint Conference on Neural Networks
IJCNN is the premier international conference in the area of neural networks theory, analysis and applications. It is organized by the International Neural Networks Society (INNS) and sponsored jointly by INNS and the IEEE Computational Intelligence Society. This is an exemplary collaboration between the two leading societies on neural networks and it provides a solid foundation for the future extensive development of the field.
Typically IJCNN conferences are held every summer.
Neural Information Processing Conference (NIPS)
The Neural Information Processing Systems (NIPS) Foundation is a non-profit corporation whose purpose is to foster the exchange of research on neural information processing systems in their biological, technological, mathematical, and theoretical aspects. Neural information processing is a field which benefits from a combined view of biological, physical, mathematical, and computational sciences.
The primary focus of the NIPS Foundation is the presentation of a continuing series of professional meetings known as the Neural Information Processing Systems Conference, held over the years at various locations in the United States and Canada. Typically NIPS conferences are held in December. NIPS 2009 will be held in Vancouver, Canada from December 7 to December 12, 2009.
World Congress on Computational Intelligence Conference (WCCI)
WCCI conferences are held every two years and it is the largest technical event in the field of computational intelligence. It hosts three conferences: the International Joint Conference on Neural Networks (IJCNN), the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), and the IEEE Congress on Evolutionary Computation (IEEE CEC). IEEE WCCI 2010 will be held in Barcelona (July 18-23, 2010), a Mediterranean city located in a privileged position on the northeastern coast of Spain. Barcelona combines history, art, architecture, and charm within a pleasant, and efficient urban environment where meet old friends, and make new ones. The congress will provide a stimulating forum for scientists, engineers, educators, and students from all over the world to discuss and present their research findings on computational intelligence.